I believe some cards at least you can make the motherboard display ports the output

He’s been writing for decades now so that should be easy to verify. I’m sure LLMs are optimized for engaging online writing that’s easy to digest

Electron I bet

This is an absurd state they are at! Weekly outages in 2025 and 2026. From developer beloved and very solid to Microslop went faster than I expected

They may have been Beloved before MS bought them. It takes awhile for technical debt to catch up.

I tried prototyping a detective game also but like you said it ends up being a wrapper for a LLM and it’s a bit chaotic, not much more fun than just talking to the LLM in a web interface or whatever

Procedural generation has always had this problem where over reliance on it feels cheap and not meaningful - see Starfield from the same developer.

I would argue the exact same effect can be seen with AI images or videos - no one is watching those for hours every day on purpose

And yet there were a lot of games with procedural generation as their centrepiece that did not suffer from this at all. The original X-Com games come to mind. I guess we can somehow "feel" where it's simulation, where it's "honest diceroll" (also very much ok when the rules appear tuned well).

But when it's too much it's too much, and an LLM game (where either the LLM remains in the loop, or it just spewed out a seemingly infinite heap of static filler) can't not be too much.

It’s still also not at all trivial to ship a capable local model with the game. If you’re hitting online APIs then that is slow and expensive and the models will get deprecated in X years.

If the median tenure is 3 years and the software business still is very profitable then people must be net useful within that 3 years. A lot of people also just don’t want to job hop much and honestly the interview culture keeps me from hopping more. I do still fall in the 3 years per hop but I’ve always had a good reason to- ie. layoffs, company going in a worse position than when I started, shit management at various levels, forever compounding responsibility…

And you can actually hand things off to them: this problem is now your problem. With AIs you’re herding cats

How is that true? As an architect when I was working at product companies, the director/CxO wasn’t going to call the junior developer to the carpet for not getting a task done or even the mid level ticket taker. Hell they don’t even know what the individual tasks are. I’m going to be the one ultimately responsible either way for project success.

Even when I was working at AWS as a mid level/L5 in the Professional Services division (lower title/lot more money), I was the one who was responsible for my “workstream” on larger projects. I couldn’t say “that’s not my fault. Blame the new L4 junior consultant who just got out of the internal boot camp for new grads”.

Now that I have moved back up to a more senior position in consulting, if a project I’m leading goes sideways, I can’t tell the customer that it’s not my fault, it’s the fault of the workstream leads and the workstream leads can’t tell me, it’s the fault of the more junior consultants who work under them. They will never talk to the client. The people under the workstream leads may not even speak English.

And that’s not meant to be an insult. The workstream leads have to he able to speak passable English and they can work with people under then who only speak Spanish.

I’ve had some who are useful almost out of school. The amount of tickets is always growing and have someone pick up those “when things calm down I swear I’ll address this” tickets is always helpful. If they can’t get anything done by themselves in the codebase then it gets much harder. I do also think that some people have completely forgotten all the context they didn’t have when they started off xx years ago so mentoring is not always very good